AutoSend MCP

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AutoSend connector, but users should treat its email-management authority and OAuth tokens carefully.

Install this only if you want OpenClaw to access and manage your AutoSend project. Use agent confirmation for any create, update, duplicate, or delete action, review generated email content before sending, install mcporter from a trusted source, and keep mcporter OAuth credential files private with user-only filesystem permissions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly documents that OAuth tokens are stored on disk in `~/.mcporter/autosend/tokens.json` but does not warn that these credentials are sensitive bearer secrets. If another local user, backup system, logs, or malware can read that file, an attacker may reuse the tokens to access the user's AutoSend account and email campaign data without re-authenticating.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal